An improved method of target detection on remote sensing image captured based on sensor network

In the optical remote sensing reconnaissance field, constrained energy minimization is a powerful method to suppress background noises and detect the target object. But when the dimension of the autocorrelation matrix becomes large, the problem is hard to be solved accurately because of the ill-conditioned matrix. In this paper, an improved energy constrained minimization method is developed for target detection on captured hyperspectral remote sensing images, which has been tested in the described experiment. The experimental result proves that, in the detection process, this method can effectively restrain noises so far as the spectral characteristics of any potential target are known, and can find sub-pixel targets out effectively from the hyperspectral remote sensing image with unknown background spectrum. This new method can effectively improve the accuracy of detection and the speed of processing when dealing with hyperspectral images with high resolution.